通过视频检测物体位置

Question

所以，我使用openCV进行基于颜色的物体检测，我在树莓派3上运行它。它正在工作，因为它实时跟踪网球（虽然它有一些延迟，因为我使用的是kinect v1 （freenect图书馆））。现在我想确定找到的对象的位置。我想知道它是在中间，还是在左边或更多在右边。我想将相机镜架分成3个部分。我会有3个布尔值，一个用于中间，一个用于左，一个用于右，然后所有3个变量将通过USB通信发送。但是，我现在已经尝试了一周来确定对象的位置，但我无法这样做。我在这里寻求帮助。

使用openCV进行对象检测的当前工作代码（我按颜色检测对象）

# USAGE
# python ball_tracking.py --video ball_tracking_example.mp4
# python ball_tracking.py

# import the necessary packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
    help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=64,
    help="max buffer size")
args = vars(ap.parse_args())

# define the lower and upper boundaries of the "green"
# ball in the HSV color space, then initialize the
# list of tracked points
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)
pts = deque(maxlen=args["buffer"])

# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
    camera = cv2.VideoCapture(0)

# otherwise, grab a reference to the video file
else:
    camera = cv2.VideoCapture(args["video"])

# keep looping
while True:
    # grab the current frame
    (grabbed, frame) = camera.read()

    # if we are viewing a video and we did not grab a frame,
    # then we have reached the end of the video
    if args.get("video") and not grabbed:
        break

    # resize the frame, blur it, and convert it to the HSV
    # color space
    frame = imutils.resize(frame, width=600)
    # blurred = cv2.GaussianBlur(frame, (11, 11), 0)
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # construct a mask for the color "green", then perform
    # a series of dilations and erosions to remove any small
    # blobs left in the mask
    mask = cv2.inRange(hsv, greenLower, greenUpper)
    mask = cv2.erode(mask, None, iterations=2)
    mask = cv2.dilate(mask, None, iterations=2)

    # find contours in the mask and initialize the current
    # (x, y) center of the ball
    cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_SIMPLE)[-2]
    center = None

    # only proceed if at least one contour was found
    if len(cnts) > 0:
        # find the largest contour in the mask, then use
        # it to compute the minimum enclosing circle and
        # centroid
        c = max(cnts, key=cv2.contourArea)
        ((x, y), radius) = cv2.minEnclosingCircle(c)
        M = cv2.moments(c)
        center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))

        # only proceed if the radius meets a minimum size
        if radius > 10:
            # draw the circle and centroid on the frame,
            # then update the list of tracked points
            cv2.circle(frame, (int(x), int(y)), int(radius),
                (0, 255, 255), 2)
            cv2.circle(frame, center, 5, (0, 0, 255), -1)
        #EDIT:
        if int(x) > int(200) & int(x) < int(400):
            middle = True
            left = False
            notleft = False

        if int(x) > int(1) & int(x) < int(200):
            left = True
            middle = False
            notleft = False

        if int(x) > int(400) & int(x) < int(600):
            notleft = True
            left = False
            middle = False

        print ("middle: ", middle, " left: ", left, " right: ", notleft)

    # update the points queue
    pts.appendleft(center)

    # loop over the set of tracked points
    for i in xrange(1, len(pts)):
        # if either of the tracked points are None, ignore
        # them
        if pts[i - 1] is None or pts[i] is None:
            continue

        # otherwise, compute the thickness of the line and
        # draw the connecting lines
        thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
        cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)

    # show the frame to our screen
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    # if the 'q' key is pressed, stop the loop
    if key == ord("q"):
        break

# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()

代码已正确评论。使用USB端口发送信息不是问题，我只是找不到，如何检测球的位置。

我正在我的树莓派上运行raspbian。

编辑： 我忘了提，我只对根据X轴的物体位置感兴趣。我认为当我将当前帧设置为600时，如果像if x > 200 && x < 400: bool middle = true那样我会写3。你不行。

EDIT2： 我想我是以某种方式让它工作，但“中间”永远不会成真。我左右都是真的，但不适合中间人。

Answer 1

        if int(x) > int(200) AND int(x) < int(400):
            middle = True
            left = False
            notleft = False

        if int(x) > int(1) AND int(x) < int(200):
            left = True
            middle = False
            notleft = False

        if int(x) > int(400) AND int(x) < int(600):
            notleft = True
            left = False
            middle = False

所有我必须写的是“和”，“＆amp;”......这么麻烦，这么一点修复。

Answer 2

如果要检测位置的对象，那么使用cv2.HoughCircles（）将比使用cv2.findContours（）更好。由于cv2.HoughCircles（）直接返回圆的中心位置（x，y）。

您可以找到使用HoughCircles（）here

的示例

如果你得到那个圆圈的中心，那么确定它的位置会很容易。

祝你好运。

Answer 3

以下是您的问题的解决方案

# import the necessary packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
    help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=32,
    help="max buffer size")
args = vars(ap.parse_args())

# define the lower and upper boundaries of the "green"
# ball in the HSV color space
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)

# initialize the list of tracked points, the frame counter,
# and the coordinate deltas
pts = deque(maxlen=args["buffer"])
counter = 0
(dX, dY) = (0, 0)
direction = ""

# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
    camera = cv2.VideoCapture(0)

# otherwise, grab a reference to the video file
else:
    camera = cv2.VideoCapture(args["video"])

# keep looping
while True:
    # grab the current frame
    (grabbed, frame) = camera.read()

    # if we are viewing a video and we did not grab a frame,
    # then we have reached the end of the video
    if args.get("video") and not grabbed:
        break

    # resize the frame, blur it, and convert it to the HSV
    # color space
    frame = imutils.resize(frame, width=600)
    # blurred = cv2.GaussianBlur(frame, (11, 11), 0)
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # construct a mask for the color "green", then perform
    # a series of dilations and erosions to remove any small
    # blobs left in the mask
    mask = cv2.inRange(hsv, greenLower, greenUpper)
    mask = cv2.erode(mask, None, iterations=2)
    mask = cv2.dilate(mask, None, iterations=2)

    # find contours in the mask and initialize the current
    # (x, y) center of the ball
    cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_SIMPLE)[-2]
    center = None

    # only proceed if at least one contour was found
    if len(cnts) > 0:
        # find the largest contour in the mask, then use
        # it to compute the minimum enclosing circle and
        # centroid
        c = max(cnts, key=cv2.contourArea)
        ((x, y), radius) = cv2.minEnclosingCircle(c)
        M = cv2.moments(c)
        center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))

        # only proceed if the radius meets a minimum size
        if radius > 10:
            # draw the circle and centroid on the frame,
            # then update the list of tracked points
            cv2.circle(frame, (int(x), int(y)), int(radius),
                (0, 255, 255), 2)
            cv2.circle(frame, center, 5, (0, 0, 255), -1)
            pts.appendleft(center)

    # loop over the set of tracked points
    for i in np.arange(1, len(pts)):
        # if either of the tracked points are None, ignore
        # them
        if pts[i - 1] is None or pts[i] is None:
            continue

        # check to see if enough points have been accumulated in
        # the buffer
        if counter >= 10 and i == 1 and pts[-10] is not None:
            # compute the difference between the x and y
            # coordinates and re-initialize the direction
            # text variables
            dX = pts[-10][0] - pts[i][0]
            dY = pts[-10][1] - pts[i][1]
            (dirX, dirY) = ("", "")

            # ensure there is significant movement in the
            # x-direction
            if np.abs(dX) > 20:
                dirX = "East" if np.sign(dX) == 1 else "West"

            # ensure there is significant movement in the
            # y-direction
            if np.abs(dY) > 20:
                dirY = "North" if np.sign(dY) == 1 else "South"

            # handle when both directions are non-empty
            if dirX != "" and dirY != "":
                direction = "{}-{}".format(dirY, dirX)

            # otherwise, only one direction is non-empty
            else:
                direction = dirX if dirX != "" else dirY

        # otherwise, compute the thickness of the line and
        # draw the connecting lines
        thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
        cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)

    # show the movement deltas and the direction of movement on
    # the frame
    cv2.putText(frame, direction, (10, 30), cv2.FONT_HERSHEY_SIMPLEX,
        0.65, (0, 0, 255), 3)
    cv2.putText(frame, "dx: {}, dy: {}".format(dX, dY),
        (10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX,
        0.35, (0, 0, 255), 1)

    # show the frame to our screen and increment the frame counter
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
    counter += 1

    # if the 'q' key is pressed, stop the loop
    if key == ord("q"):
        break

# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()